Map abnormal road section determination method, computing device and storage medium
By automatically obtaining abnormal records and location information of the vehicle when driving on the map, the problem of low efficiency and insufficient accuracy of manual acquisition of abnormal sections of the map is solved, and efficient and accurate matching of abnormal sections is achieved.
Patent Information
- Application Number
- CN202411930950.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-24
- Publication Date
- 2025-04-18
AI Technical Summary
In the prior art, manual acquisition of abnormal map sections is inefficient and not accurate enough, especially when the map coverage is expanded, it is difficult to efficiently match abnormal sections.
By obtaining the correspondence between abnormal records, location information and time information when driving based on the map, the abnormal road section of the map is automatically determined. The specific steps include obtaining exception records, determining the real trigger time interval, obtaining the correspondence between location information and time information, and determining the abnormal road section of the map based on this information.
It realizes automatic acquisition of abnormal map sections, improves efficiency and accuracy, can cope with larger map coverage, and significantly improves the matching accuracy of abnormal road sections.
Smart Images
Figure CN119851238A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of autonomous driving technology, and in particular to a method for determining abnormal road sections on a map, a computing device, and a storage medium. Background Art
[0002] With the development of autonomous driving and assisted driving functions, vehicle systems gradually rely on high-precision maps (HDMap) or standard maps (SDMap) for path planning, lane changes, turns, and other operations. In order to ensure the correctness of the system, on-vehicle real-vehicle testing is required to verify the quality of the map. However, the existing manual testing method manually records the time and location of the abnormality and matches the abnormal road section with the HDMap or standard map. This method has the following problems:
[0003] Manual acquisition of abnormal map sections is inefficient, especially when map coverage gradually expands, the difficulty of manual acquisition increases further; manual matching of abnormal records with abnormal map sections is often not accurate enough, and high-precision verification cannot be achieved.
[0004] Accordingly, the art needs a new solution for determining abnormal road sections on a map to solve the above problems. Summary of the invention
[0005] In order to overcome the above-mentioned defects, the present application is proposed to solve or at least partially solve the technical problem of low efficiency and insufficient accuracy in manually obtaining abnormal road sections on maps.
[0006] In a first aspect, a method for determining an abnormal road section on a map is provided, wherein the map is a high-precision map or a standard map, and the method comprises:
[0007] Acquiring abnormal records when the vehicle is driven based on the map, wherein the abnormal records include abnormal driving behavior records of the driver and / or abnormal vehicle function records;
[0008] Determine a real trigger time interval corresponding to the exception based on the exception record;
[0009] Acquire the correspondence between the position information and the time information of the vehicle when driving based on the map;
[0010] The abnormal road section on the map is determined based on the actual trigger time interval corresponding to the abnormality and the corresponding relationship.
[0011] In a technical solution of the above-mentioned method for determining abnormal road sections on a map, determining the actual triggering time interval corresponding to the abnormality based on the abnormality record includes:
[0012] Obtain the map road section abnormality type corresponding to the abnormal record and the reporting completion time of the abnormality;
[0013] The actual triggering time interval corresponding to the abnormality is determined based on the map road section abnormality type and the reporting completion time.
[0014] In a technical solution of the above-mentioned method for determining abnormal road sections on a map, the map road section abnormality type includes a single point abnormality or a road section abnormality; and the determining of a real trigger time interval corresponding to the abnormality based on the map road section abnormality type and the reporting completion time includes:
[0015] Determine the time difference between the reporting completion time and the actual triggering time corresponding to the abnormality based on the map road section abnormality type;
[0016] The actual trigger time interval is determined based on the time difference and the reporting completion time.
[0017] In a technical solution of the above-mentioned method for determining abnormal road sections on a map, determining the time difference between the reporting completion time and the actual triggering time corresponding to the abnormality based on the abnormal type of the map road section includes:
[0018] If the map road section anomaly type is a single point anomaly, determining a first time difference based on historical anomaly data;
[0019] If the map road section anomaly type is a road section anomaly, a second time difference is determined based on historical anomaly data and a preset reporting time interval.
[0020] In a technical solution of the above-mentioned method for determining abnormal road sections on a map, when the abnormal type of the road section on the map is a single-point abnormality, the real trigger time interval is a single-point time, and determining the real trigger time interval based on the time difference and the reporting completion time includes:
[0021] Obtain the result of subtracting the absolute value of the first time difference from the reporting completion time;
[0022] The single point time corresponding to the result is used as the real trigger time interval.
[0023] In a technical solution of the above-mentioned method for determining abnormal road sections on a map, when the map road section abnormality type is road section abnormality, determining the real trigger time interval based on the time difference and the reporting completion time includes:
[0024] Obtaining a difference between the reporting completion time and the absolute value of the second time difference, and taking the difference as a first endpoint of the real trigger time interval;
[0025] Obtaining a result of adding the first endpoint to the reporting time interval, and taking the result of the addition as a second endpoint of the real trigger time interval;
[0026] A closed interval formed by the first endpoint and the second endpoint is used as the real trigger time interval.
[0027] In a technical solution of the above-mentioned method for determining an abnormal road section on a map, the determining of the abnormal road section on the map based on the real trigger time interval corresponding to the abnormality and the corresponding relationship includes:
[0028] Determining, according to the actual trigger time interval and the corresponding relationship, a road section unit on the map corresponding to the actual trigger time interval;
[0029] Aggregating the road section units corresponding to the real trigger time interval;
[0030] The abnormal road section of the map is determined based on the aggregation result.
[0031] In a technical solution of the above-mentioned method for determining abnormal map sections, the determining of the abnormal map sections based on the aggregation result further includes:
[0032] Determine whether there is a missed report in the road section unit corresponding to the real trigger time interval;
[0033] If so, the abnormal road section on the map is determined based on the missed road section unit and the road section unit corresponding to the actual trigger time interval.
[0034] In a technical solution of the above-mentioned method for determining abnormal road sections on a map, the method further includes:
[0035] Obtaining abnormal records of multiple vehicles driving based on the map, and obtaining the identity of each vehicle;
[0036] According to the identity identifier, based on the abnormal record of each vehicle, determine the actual trigger time interval corresponding to the abnormality; and obtain the corresponding relationship between the position information and the time information of each vehicle when driving based on the map;
[0037] The abnormal road section of the map is determined based on the real trigger time intervals corresponding to the abnormalities of the multiple vehicles and the corresponding relationship.
[0038] In a technical solution of the above-mentioned method for determining abnormal map sections, the method further includes visualizing the abnormal map sections, wherein the abnormal map sections are set to different levels according to different times that the section units in the abnormal map sections are determined.
[0039] In a second aspect, a computing device is provided, comprising at least one processor; and a memory communicatively connected to the at least one processor; wherein a computer program is stored in the memory, and when the computer program is executed by the at least one processor, the method described in any one of the technical solutions of the above-mentioned method for determining abnormal road sections on a map is implemented.
[0040] In a third aspect, a computer-readable storage medium is provided, wherein a plurality of program codes are stored therein, wherein the program codes are suitable for being loaded and run by a processor to execute the method described in any one of the technical solutions of the above-mentioned method for determining abnormal road sections on a map.
[0041] Solution 1. A method for determining abnormal road sections in a map, wherein the map is a high-precision map or a standard map, and the method comprises:
[0042] Acquiring abnormal records when the vehicle is driven based on the map, wherein the abnormal records include abnormal driving behavior records of the driver and / or abnormal vehicle function records;
[0043] Determine a real trigger time interval corresponding to the exception based on the exception record;
[0044] Acquire the correspondence between the position information and the time information of the vehicle when driving based on the map;
[0045] The abnormal road section on the map is determined based on the actual trigger time interval corresponding to the abnormality and the corresponding relationship.
[0046] Solution 2. According to the method of Solution 1, determining the actual trigger time interval corresponding to the anomaly based on the anomaly record comprises:
[0047] Obtain the map road section abnormality type corresponding to the abnormal record and the reporting completion time of the abnormality;
[0048] The actual triggering time interval corresponding to the abnormality is determined based on the map road section abnormality type and the reporting completion time.
[0049] Solution 3. According to the method of Solution 2, the map section abnormality type includes a single point abnormality or a section abnormality; and the actual triggering time interval corresponding to the abnormality is determined based on the map section abnormality type and the reporting completion time, including:
[0050] Determine the time difference between the reporting completion time and the actual triggering time corresponding to the abnormality based on the map road section abnormality type;
[0051] The actual trigger time interval is determined based on the time difference and the reporting completion time.
[0052] Solution 4. According to the method of Solution 3, determining the time difference between the reporting completion time and the actual triggering time corresponding to the abnormality based on the abnormality type of the map section includes:
[0053] If the map road section anomaly type is a single point anomaly, determining a first time difference based on historical anomaly data;
[0054] If the map road section anomaly type is a road section anomaly, a second time difference is determined based on historical anomaly data and a preset reporting time interval.
[0055] Solution 5. According to the method of Solution 4, when the map section abnormality type is a single point abnormality, the real trigger time interval is a single point time, and determining the real trigger time interval based on the time difference and the reporting completion time includes:
[0056] Obtain the result of subtracting the absolute value of the first time difference from the reporting completion time;
[0057] The single point time corresponding to the result is used as the real trigger time interval.
[0058] Solution 6. According to the method of Solution 4, when the map section abnormality type is a section abnormality, determining the real trigger time interval based on the time difference and the reporting completion time includes:
[0059] Obtaining a difference between the reporting completion time and the absolute value of the second time difference, and taking the difference as a first endpoint of the real trigger time interval;
[0060] Obtaining a result of adding the first endpoint to the reporting time interval, and using the result of the addition as a second endpoint of the real trigger time interval;
[0061] A closed interval formed by the first endpoint and the second endpoint is used as the real trigger time interval.
[0062] Solution 7. According to the method of Solution 1, determining the abnormal road section on the map based on the real trigger time interval corresponding to the abnormality and the corresponding relationship includes:
[0063] Determine, according to the actual trigger time interval and the corresponding relationship, a road section unit on the map corresponding to the actual trigger time interval;
[0064] Aggregating the road section units corresponding to the real trigger time interval;
[0065] The abnormal road section of the map is determined based on the aggregation result.
[0066] Solution 8. The method according to Solution 7, wherein determining the abnormal road section on the map based on the aggregation result further includes:
[0067] Determine whether there is a missed report in the road section unit corresponding to the real trigger time interval;
[0068] If so, the abnormal road section on the map is determined based on the missed road section unit and the road section unit corresponding to the actual trigger time interval.
[0069] Solution 9. The method according to Solution 1, further comprising:
[0070] Obtaining abnormal records of multiple vehicles driving based on the map, and obtaining the identity of each vehicle;
[0071] According to the identity identifier, based on the abnormal record of each vehicle, determine the actual trigger time interval corresponding to the abnormality; and obtain the corresponding relationship between the position information and the time information of each vehicle when driving based on the map;
[0072] The abnormal road section of the map is determined based on the real trigger time intervals corresponding to the abnormalities of the multiple vehicles and the corresponding relationship.
[0073] Solution 10. The method according to Solution 8 further comprises visualizing the abnormal map section, wherein the abnormal map section is set to different levels according to the number of times the section unit in the abnormal map section is determined.
[0074] Solution 11. A computing device comprising:
[0075] at least one processor;
[0076] and, a memory communicatively coupled to the at least one processor;
[0077] The memory stores a computer program, and when the computer program is executed by the at least one processor, the method for determining abnormal road sections on a map described in any one of Schemes 1 to 10 is implemented.
[0078] Solution 12. A computer-readable storage medium storing a plurality of program codes, wherein the program codes are suitable for being loaded and run by a processor to execute the method for determining abnormal road sections on a map according to any one of Solutions 1 to 10.
[0079] The above one or more technical solutions of the present application have at least one or more of the following beneficial effects:
[0080] In the technical solution of the method for determining abnormal map sections provided in the present application, the abnormal map sections are automatically acquired based on the correspondence between abnormal records, location information and time information when the vehicle is driving based on the map, without the need for manual matching. This can greatly improve the efficiency of acquiring abnormal map sections, effectively cope with a larger map coverage range, and improve the degree of accuracy. BRIEF DESCRIPTION OF THE DRAWINGS
[0081] The disclosure of the present application will become easier to understand with reference to the accompanying drawings. It is easy for those skilled in the art to understand that these drawings are only for illustrative purposes and are not intended to limit the scope of protection of the present application. Among them:
[0082] Figure 1 is a flowchart of the main steps of a method for determining abnormal road sections on a map according to an embodiment of the present application;
[0083] Figure 2 is a schematic diagram of the aggregation result output interface according to an embodiment of the present application;
[0084] Figures 3A-3C is a visual verification diagram according to an embodiment of the present application; wherein Figure 3A It is a schematic diagram of simulation points. Figure 3B This is a schematic diagram of abnormal road sections on a high-precision map. Figure 3C It is a schematic diagram of abnormal road sections on the standard map;
[0085] Figure 4 It is a schematic diagram of the main structure of a computing device according to an embodiment of the present application.
[0086] Reference numerals:
[0087] 400: computing device; 401: processor; 402: memory; 403: computer program. DETAILED DESCRIPTION
[0088] Some embodiments of the present application are described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present application and are not intended to limit the protection scope of the present application.
[0089] In the description of the present application, "module" and "processor" may include hardware, software or a combination of the two. A module may include hardware circuits, various suitable sensors, communication ports, memory, and may also include software parts, such as program code, or a combination of software and hardware. The processor may be a central processing unit, a microprocessor, an image processor, a digital signal processor or any other suitable processor. The processor has data and / or signal processing functions. The processor may be implemented in software, hardware or a combination of the two. Computer-readable storage media include any suitable medium that can store program code, such as a disk, a hard disk, an optical disk, a flash memory, a read-only memory, a random access memory, etc. The term "A and / or B" means all possible combinations of A and B, such as only A, only B or A and B. The term "at least one A or B" or "at least one of A and B" has a similar meaning to "A and / or B" and may include only A, only B or A and B. The singular terms "one" and "the" may also include plural forms.
[0090] The directional terms used in this document, such as "front", "front side", "front part", "rear", "rear side" and "rear part", are based on the front-to-back direction of the vehicle after the component is installed on the vehicle. The "longitudinal", "longitudinal" and "longitudinal section" mentioned in this document are based on the front-to-back direction after the component is installed on the vehicle, while "transverse", "transverse" and "cross section" refer to the direction perpendicular to the longitudinal direction.
[0091] The relevant user personal information that may be involved in the various embodiments of this application is strictly in accordance with the requirements of laws and regulations, following the principles of legality, legitimacy and necessity, based on the reasonable purposes of business scenarios, to process the personal information that users actively provide during the use of products / services or generated due to the use of products / services, as well as the personal information obtained with the user's authorization.
[0092] The user personal information processed by this application will vary depending on the specific product / service scenario, and shall be based on the specific scenario in which the user uses the product / service, and may involve the user's account information, device information, driving information, vehicle information or other related information. This application will treat the user's personal information and its processing with a high degree of diligence.
[0093] This application attaches great importance to the security of user personal information and has taken reasonable and feasible security protection measures that meet industry standards to protect user information and prevent personal information from being accessed, disclosed, used, modified, damaged or lost without authorization.
[0094] Before the autonomous driving function is enabled in an open area, it is usually necessary to test the area and mark the road sections where abnormalities frequently occur during the test on a map and put them on a blacklist in the opened area to ensure the safety of autonomous driving and facilitate subsequent optimization.
[0095] The present application provides a method for determining abnormal road sections on a map.
[0096] Please refer to the attached Figure 1 , Figure 1 FIG. 1 is a flowchart of the main steps of a method for determining abnormal road sections on a map according to an embodiment of the present application. Figure 1 As shown, the map is a high-precision map or a standard map, and the method for determining abnormal road sections in the map in the embodiment of the present application mainly includes the following steps S1 to S4.
[0097] Step S1, obtaining abnormal records when the vehicle is driving based on the map, wherein the abnormal records include abnormal driving behavior records of the driver and / or abnormal vehicle function records.
[0098] For example, in one embodiment, the abnormal driving behavior record of the driver includes abnormal driving behaviors such as wrong braking, sudden braking, lane change on a solid line, driving on the line, running a red light / yellow light, etc.; the abnormal vehicle function record includes abnormal vehicle function phenomena such as inability to enter the NAD (Navigation Assisted Driving) function, abnormal NAD degradation / exit, NAD flashback / flashin, instrument guide line distortion, lane line display error, etc. Specifically, those skilled in the art can set abnormal labels according to actual needs so as to report during testing.
[0099] Step S2: determining a real triggering time interval corresponding to the anomaly based on the anomaly record.
[0100] In one embodiment, determining the actual trigger time interval corresponding to the exception based on the exception record includes:
[0101] Obtain the map road section abnormality type corresponding to the abnormal record and the reporting completion time of the abnormality;
[0102] The actual triggering time interval corresponding to the abnormality is determined based on the map road section abnormality type and the reporting completion time.
[0103] For example, the anomaly can be obtained through manual recording by the driver or camera recording, and reported; the driver can report it in the vehicle or remotely.
[0104] A reporting time interval is preset before an exception is reported; during the exception reporting process, a report is made once an exception is obtained. If the duration of this exception is long, a report is made every time the reporting time interval passes after the reporting completion time until the exception ends.
[0105] In one embodiment, the map section anomaly type includes a single point anomaly or a section anomaly; and determining the actual trigger time interval corresponding to the anomaly based on the map section anomaly type and the reporting completion time includes:
[0106] Determine the time difference between the reporting completion time and the actual triggering time corresponding to the abnormality based on the map road section abnormality type;
[0107] The actual trigger time interval is determined based on the time difference and the reporting completion time.
[0108] Among them, a single-point anomaly refers to an anomaly that occurs only at a specific location, and the problem is limited to that location. A single-point anomaly corresponds to one anomaly report, such as running a red light due to an error in the stop line position produced by the map.
[0109] A road section problem refers to an abnormality that occurs on a road section, usually involving a persistent problem on that road section. Depending on the duration of the road section abnormality, a road section abnormality can correspond to one or more abnormality reports. For example, due to an abnormality in the production of driving points on the map, vehicles on that road section continue to have abnormal behaviors such as lane deviation.
[0110] Further, in one embodiment, the determining, based on the map section abnormality type, the time difference between the reporting completion time corresponding to the abnormality and the actual triggering time includes:
[0111] If the map road section anomaly type is a single point anomaly, determining a first time difference based on historical anomaly data;
[0112] If the map road section anomaly type is a road section anomaly, a second time difference is determined based on historical anomaly data and a preset reporting time interval.
[0113] In one embodiment, when the map road section anomaly type is a single point anomaly, the real trigger time interval is a single point time, and determining the real trigger time interval based on the time difference and the reporting completion time includes:
[0114] Obtain the result of subtracting the absolute value of the first time difference from the reporting completion time;
[0115] The single point time corresponding to the result is used as the real trigger time interval.
[0116] For example, in one embodiment, the format of the reporting completion time tag_date is YYYY-MM-DDHH:MM:SS. In order to facilitate subsequent processing, tag_date can be converted into a UNIX timestamp first.
[0117] The conversion code is: cast(UNIX_TIMESTAMP(tag_date)*1e9 as bigint)as tag_ts, and a tag_ts (report completion timestamp) is obtained, which indicates the nanosecond timestamp of the exception reporting completion time.
[0118] In this embodiment, the first time difference Δt1 = 3 s is determined based on historical abnormal data.
[0119] The code of the actual trigger time interval is as follows:
[0120] when time_type='single point'then concat('[',cast(tag_ts-3*1e9 asbigint),',',cast(tag_ts-3*1e9 as bigint),']')
[0121] The single point time is (tag_ts-3s), and it is considered that the time when the exception occurs is 3 seconds before the reporting completion time.
[0122] In another embodiment, when the map section abnormality type is a section abnormality, determining the real trigger time interval based on the time difference and the reporting completion time includes:
[0123] Obtaining a difference between the reporting completion time and the absolute value of the second time difference, and taking the difference as a first endpoint of the real trigger time interval;
[0124] Obtaining a result of adding the first endpoint to the reporting time interval, and taking the result of the addition as a second endpoint of the real trigger time interval;
[0125] A closed interval formed by the first endpoint and the second endpoint is used as the real trigger time interval.
[0126] In this embodiment, the reporting time interval is 10 seconds, and the second time difference Δt2=9 seconds is determined based on historical abnormal data.
[0127] If the second time difference value determined based on the historical abnormal data is greater than the reporting time interval, the second time difference value needs to be corrected to be less than the reporting time interval.
[0128] The code of the actual trigger time interval is as follows:
[0129] when time_type='section'and(have_hdmap is null or have_hdmap='false')then concat('[',cast(tag_ts-9*1e9 as bigint),',',cast(tag_ts+1e9 asbigint),']')
[0130] Among them, the first endpoint is (tag_ts-9s), and the second endpoint is (tag_ts+1s); it is considered that the time when the exception occurs is 9 seconds before the reporting completion time, and the time when the exception ends is 1 second after the reporting completion time.
[0131] Step S3, obtaining the correspondence between the position information and the time information of the vehicle when driving based on the map.
[0132] In one embodiment, the corresponding relationship can be determined based on the real-time updated position information and time information of the vehicle. Exemplarily, the position information and time information are updated once per second. Specifically, the position information is represented by coordinates on the high-precision map or the standard map.
[0133] Step S4: determining the abnormal road section on the map based on the actual trigger time interval corresponding to the abnormality and the corresponding relationship.
[0134] In one embodiment, the determining the abnormal road section on the map based on the real trigger time interval corresponding to the abnormality and the corresponding relationship includes:
[0135] Determine, according to the actual trigger time interval and the corresponding relationship, a link on the map corresponding to the actual trigger time interval;
[0136] Aggregating the road section units corresponding to the real trigger time interval;
[0137] The abnormal road section of the map is determined based on the aggregation result.
[0138] Among them, Link is the basic unit of the map, and a road section is usually composed of multiple links. Specifically, the road section unit in HDMap is HDlink, and for example, the road can be divided into multiple HDlinks; the road section unit in SDMap is SDlink, and for example, the road can be finely represented by lane lines, and the lane lines can be divided into multiple SDlinks. By setting a code (link_id) for each link, it is easy to find and correspond to the map coordinates.
[0139] In this embodiment, according to the real trigger time interval and the corresponding relationship, the coordinates of the vehicle passing within the real trigger time interval are searched, and further the link corresponding to the coordinates can be obtained.
[0140] The link (ie, abnormal link) corresponding to the actual trigger time interval is aggregated. Exemplarily, for each abnormal report, the aggregation result includes at least the reporting completion time, the actual trigger time interval, and the corresponding link_id.
[0141] In order to efficiently conduct autonomous driving function activation tests and eliminate accidental interference, multiple vehicles are usually used for testing.
[0142] In another embodiment of the present application, the method further comprises:
[0143] Acquire abnormal records of multiple vehicles when driving based on the map, and simultaneously acquire an identity identifier (VID) of each vehicle;
[0144] According to the identity identifier, based on the abnormal record of each vehicle, determine the actual trigger time interval corresponding to the abnormality; and obtain the corresponding relationship between the position information and the time information of each vehicle when driving based on the map;
[0145] The abnormal road section of the map is determined based on the real trigger time intervals corresponding to the abnormalities of the multiple vehicles and the corresponding relationship.
[0146] In one embodiment, the code involved in the link aggregation process is as follows:
[0147] First, start_utc_ts (start timestamp) and end_utc_ts (end timestamp) are extracted from the real trigger time interval hdlink_utc_ts corresponding to the anomaly.
[0148] CAST(json_extract(hdlink_utc_ts,'$[0]')AS BIGINT)AS start_utc_ts,
[0149] CAST(json_extract(hdlink_utc_ts,'$[1]')AS BIGINT)AS end_utc_ts
[0150] The relevant hdlink / sdlink is further matched by the vehicle identification (vehicle_id) and the real trigger time interval to find out the hdlink / sdlink that overlaps with the real trigger time interval.
[0151] Among them, if the start time of the exception (start_utc_ts) is earlier than the end time of hdlink (end_ts), and the end time of the exception (end_utc_ts) is later than the start time of hdlink (begin_ts), then the two time periods overlap.
[0152] All matched hd_link_ids are aggregated into an array through the array_agg function to form a result set hd_link_list for subsequent processing.
[0153] SELECT array_agg(hd_link_id)AS hd_link_list
[0154] FROM(SELECT e.*,link_his.hd_link_id from split_event e
[0155] LEFT join link_his on e.vehicle_id=link_his.vehicle_id and
[0156] (e.start_utc_ts<link_his.end_ts AND e.end_utc_ts> link_his.begin_ts)
[0157] The result set obtained by the above method is the aggregation result.
[0158] Furthermore, a table may be output according to the aggregation result.
[0159] In one embodiment, the output content of the aggregation result includes: an abnormality code (data_id), a unique identifier (uuid), an abnormality tag (tag_type), an abnormality type (time_type), and a specific abnormality description (proble_describe) for identifying an abnormality; a vehicle identification code (vin) and a vehicle identity (vehicle_id) related to the vehicle, a test date (test_date) related to time, a reporting completion time (tag_date), an update date (update_date), and an abnormal link list (hd_link_list), etc. The abnormal link list includes all link_ids corresponding to the actual trigger time interval.
[0160] This application uses the above method to automatically match abnormal records with abnormal links, and obtains abnormal road sections on the map accurately to the link, which greatly improves the accuracy.
[0161] Please refer to the attached Figure 2 , Figure 2 It is a schematic diagram of the aggregation result output interface according to an embodiment of the present application.
[0162] Further, the abnormal road section of the map is determined based on the aggregation result. The link corresponding to the real trigger time interval is called an abnormal link, and the link not corresponding to the real trigger time interval is called a normal link.
[0163] In one embodiment, the aggregation result can be directly used as the determination result of the abnormal map section, where the abnormal link is the abnormal map section; in another embodiment, multiple continuous abnormal links can be combined and marked as one abnormal map section to make it easier to show on the map.
[0164] Furthermore, in one embodiment, the determining the abnormal road section on the map based on the aggregation result further includes:
[0165] Determine whether there is a missed report in the road section unit corresponding to the real trigger time interval;
[0166] If so, the abnormal road section on the map is determined based on the missed road section unit and the road section unit corresponding to the actual trigger time interval.
[0167] For example, if there are a small number of normal links among multiple consecutive abnormal links, and if the ratio of normal links to abnormal links is judged to be less than a preset false negative threshold, these small number of normal links are considered to be false negatives, and are added to the aggregation results together with the abnormal links to determine the abnormal road section of the map.
[0168] Furthermore, in one embodiment, the method further comprises visualizing the abnormal map section, wherein the abnormal map section is set to different levels according to different times that the section units in the abnormal map section are determined.
[0169] Exemplarily, the links in the abnormal road section of the map are ranked from high to low according to the number of times they are marked as abnormal links, and are distinguished by different colors, so that the marking of the abnormal road section of the map is more intuitive.
[0170] Based on the method described in the above steps S1 to S4, the abnormal map sections are automatically acquired according to the correspondence between the abnormal records, location information and time information when the vehicle is driving based on the map, without the need for manual matching. This can greatly improve the efficiency of acquiring abnormal map sections, effectively cope with a larger map coverage range, and improve the accuracy.
[0171] Further, in order to verify the above-mentioned map abnormal road section determination method, this application provides the following embodiments, please refer to Figures 3A-3C .
[0172] Figures 3A-3C is a visual verification diagram according to an embodiment of the present application; wherein Figure 3A It is a schematic diagram of simulation points. Figure 3B This is a schematic diagram of abnormal road sections on a high-precision map. Figure 3C It is a schematic diagram of abnormal road sections on the standard map.
[0173] in, Figure 3A The positions circled by the dotted circles are abnormal simulation points. When the vehicle passes through these simulation points, the driver reports the abnormality.
[0174] exist Figure 3B In the high-precision map of , the position encircled by the dotted line is the abnormal road section of the map determined in this embodiment; Figure 3B In the standard map, the position encircled by the dotted line is the abnormal road section of the map determined in this embodiment.
[0175] By comparison, it can be seen that, regardless of high-precision maps or standard maps, the above technical solution can match the abnormal road sections of the map with the simulated points to obtain the expected results.
[0176] It should be pointed out that although the various steps in the above embodiments are described in a specific order, those skilled in the art can understand that in order to achieve the effect of the present application, different steps do not have to be executed in such an order. They can be executed simultaneously (in parallel) or in other orders. These adjusted schemes are equivalent to the technical schemes described in this application, and therefore will also fall within the scope of protection of this application.
[0177] It is understood by those skilled in the art that all or part of the processes in the method for implementing the above-mentioned embodiment of the present application can also be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable storage medium may include: any entity or device, medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory, random access memory, electrical carrier signal, telecommunication signal and software distribution medium, etc. that can carry the computer program code.
[0178] Another aspect of the present application also provides a computing device.
[0179] See also Figure 4 , Figure 4 It is a schematic diagram of the main structure of a computing device according to an embodiment of the present application.
[0180] In an embodiment of a computing device according to the present application, the computing device 400 may include at least one processor 401; and a memory 402 in communication with the at least one processor 401; wherein the memory 402 stores a computer program 403, and when the computer program 403 is executed by the at least one processor 401, the method described in any of the above embodiments is implemented. The computing device 400 described in the present application may include a driving device, a smart car, a robot, and other devices. Exemplarily, the memory 402 and the processor 401 are in communication with each other via a bus.
[0181] In some embodiments of the present application, the computing device may further include at least one sensor for sensing information. The sensor is communicatively connected to any type of processor mentioned in the present application. Optionally, the computing device may further include an autonomous driving system for guiding the computing device to drive itself or assist in driving. The processor communicates with the sensor and / or the autonomous driving system to complete the method described in any of the above embodiments.
[0182] Another aspect of the present application also provides a computer-readable storage medium.
[0183] In an embodiment of a computer-readable storage medium according to the present application, the computer-readable storage medium may be configured to store a program for executing the map abnormal road section determination method of the above method embodiment, and the program may be loaded and run by a processor to implement the above map abnormal road section determination method. For ease of explanation, only the parts related to the embodiment of the present application are shown. For specific technical details not disclosed, please refer to the method part of the embodiment of the present application. The computer-readable storage medium may be a storage device formed by various electronic devices. Optionally, the computer-readable storage medium in the embodiment of the present application is a non-temporary computer-readable storage medium.
[0001] In the above embodiments, the description of each embodiment has its own emphasis. For the part not described or recorded in detail in a certain embodiment, please refer to the relevant description of other embodiments. All the above optional technical solutions can be combined arbitrarily to form optional embodiments of the present application, which will not be described one by one here.
[0184] So far, the technical solution of the present application has been described in conjunction with an embodiment shown in the accompanying drawings, but it is easy for those skilled in the art to understand that the protection scope of the present application is obviously not limited to these specific embodiments. Without departing from the principles of the present application, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present application.
Claims
1. A method for determining abnormal road sections on a map, characterized in that: The map is a high-precision map or a standard map, and the method includes: Acquiring abnormal records when the vehicle is driven based on the map, wherein the abnormal records include abnormal driving behavior records of the driver and / or abnormal vehicle function records; Determine a real trigger time interval corresponding to the exception based on the exception record; Acquire the correspondence between the position information and the time information of the vehicle when driving based on the map; The abnormal road section on the map is determined based on the actual trigger time interval corresponding to the abnormality and the corresponding relationship.
2. The method according to claim 1, characterized in that Determining the actual trigger time interval corresponding to the exception based on the exception record includes: Obtain the map road section abnormality type corresponding to the abnormal record and the reporting completion time of the abnormality; The actual triggering time interval corresponding to the abnormality is determined based on the map road section abnormality type and the reporting completion time.
3. The method according to claim 2, characterized in that The map section anomaly type includes a single point anomaly or a section anomaly; and the actual trigger time interval corresponding to the anomaly is determined based on the map section anomaly type and the reporting completion time, including: Determine the time difference between the reporting completion time and the actual triggering time corresponding to the abnormality based on the map road section abnormality type; The actual trigger time interval is determined based on the time difference and the reporting completion time.
4. The method according to claim 3, characterized in that The determining of the time difference between the reporting completion time and the actual triggering time corresponding to the abnormality based on the map section abnormality type includes: If the map road section anomaly type is a single point anomaly, determining a first time difference based on historical anomaly data; If the map road section anomaly type is a road section anomaly, a second time difference is determined based on historical anomaly data and a preset reporting time interval.
5. The method according to claim 4, characterized in that When the map road section anomaly type is a single point anomaly, the real trigger time interval is a single point time, and determining the real trigger time interval based on the time difference and the reporting completion time includes: Obtain the result of subtracting the absolute value of the first time difference from the reporting completion time; The single point time corresponding to the result is used as the real trigger time interval.
6. The method according to claim 4, characterized in that When the map section abnormality type is a section abnormality, determining the real trigger time interval based on the time difference and the reporting completion time includes: Obtaining a difference between the reporting completion time and the absolute value of the second time difference, and taking the difference as a first endpoint of the real trigger time interval; Obtaining a result of adding the first endpoint to the reporting time interval, and taking the result of the addition as a second endpoint of the real trigger time interval; A closed interval formed by the first endpoint and the second endpoint is used as the real trigger time interval.
7. The method according to claim 1, characterized in that The determining the abnormal road section on the map based on the real trigger time interval corresponding to the abnormality and the corresponding relationship includes: Determining, according to the actual trigger time interval and the corresponding relationship, a road section unit on the map corresponding to the actual trigger time interval; Aggregating the road section units corresponding to the real trigger time interval; The abnormal road section of the map is determined based on the aggregation result.
8. The method according to claim 7, characterized in that The determining the abnormal road section on the map based on the aggregation result further includes: Determine whether there is a missed report in the road section unit corresponding to the real trigger time interval; If so, the abnormal road section on the map is determined based on the missed road section unit and the road section unit corresponding to the actual trigger time interval.
9. The method according to claim 1, characterized in that: The method further comprises: Obtaining abnormal records of multiple vehicles driving based on the map, and obtaining the identity of each vehicle; According to the identity identifier, based on the abnormal record of each vehicle, determine the actual trigger time interval corresponding to the abnormality; and obtain the corresponding relationship between the position information and the time information of each vehicle when driving based on the map; The abnormal road section of the map is determined based on the real trigger time intervals corresponding to the abnormalities of the multiple vehicles and the corresponding relationship.
10. The method according to claim 8, characterized in that The method further includes visualizing the abnormal map section, wherein the abnormal map section is set to different levels according to different times that the section units in the abnormal map section are determined.